International Conference on Computer and Knowledge Engineering

Please wait ...

Home / 14th International Conference on Computer and Knowledge Engineering

Non-Negative Matrix Factorization improves Residual Neural Networks

Authors :

Hojjat Moayed¹

1- Esfarayen University of Technology

Keywords :

ResNet،Residual Neural Network،NMF،Deep Learning

Abstract :

Residual neural networks enable the use of very deep architectures. These architectures benefit by passing the identity information from a layer directly to subsequent layers. Extensive research has been conducted to improve the performance of residual neural networks. In this paper, we propose a method to improve performance by providing a more informative input using non-negative matrix factorization. The method combines the invariant features learned from the training data with the extracted, fine-tuned features at the end of the residual block. Our experimental results confirm that the proposed architecture improves performance on the image classification task.

List of archived papers

Damage Detection After the Earthquake Using Sentinel-1 and 2 Images and Machine Learning Algorithms (Case Study: Sarpol-e Zahab Earthquake)

Niloofar Alizadeh - Behnam Asghari Beirami - Mehdi Mokhtarzade

Optimal PMU Placement Considering Reliability of Measurement System in Smart Grids

Mohammad Shahraeini - Shahla Khormali - Ahad Alvandi

An Efficient Approach for Breast Abnormality Detection through High-Level Features of Thermography Images

Farhad Abedinzadeh Torghabeh - Yeganeh Modaresnia - Seyyed Abed Hosseini

Automatic Detection and Risk Assessment of Session Management Vulnerabilities in Web Applications

Nasrin Garmabi - Mohammad Ali Hadavi

A scalable blockchain-based educational network for data storage and assessment

Maryam Fattahi Vanani - Hamidreza Shayegh Borujeni - Ali Nourollah

Segmentation of Hard Exudates in Retinal Fundus Images Using BCDU-Net

Nafise Ameri - Nasser Shoeibi - Mojtaba Abrishami

Histopathology Image-Based Cancer Classification Utilizing Transfer Learning Approach

Amir Meydani - Alireza Meidani - Ali Ramezani - Maryam Shabani - Mohammad Mehdi Kazeminasab - Shahriar Shahablavasani

PowerLinear Activation Functions with application to the first layer of CNNs

Kamyar Nasiri - Kamaledin Ghiasi-Shirazi

Automated Person Identification from Hand Images\\using Hierarchical Vision Transformer Network

Zahra Ebrahimian - Seyed Ali Mirsharji - Ramin Toosi - Mohammad Ali Akhaee

Spatio-Temporal Graph Neural Networks for Accurate Crime Prediction

Rojan Roshankar - Mohammad Reza Keyvanpour

more

Samin Hamayesh - Version 44.12.3